Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1337 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.9771. Min Act: -0.1700

Data Index: 2010813 (Open Web Text)

Max Activating Token Index: 147

Text #1

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.9491. Min Act: -0.1700

Data Index: 4000324 (Open Web Text)

Max Activating Token Index: 41

Text #2

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.9301. Min Act: -0.1694

Data Index: 7824999 (Open Web Text)

Max Activating Token Index: 165

Text #3

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.9265. Min Act: -0.1700

Data Index: 2186291 (Open Web Text)

Max Activating Token Index: 24

Text #4

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.9259. Min Act: -0.1700

Data Index: 4892490 (Open Web Text)

Max Activating Token Index: 66

Text #5

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.9217. Min Act: -0.1700

Data Index: 3701688 (Open Web Text)

Max Activating Token Index: 54

Text #6

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.9170. Min Act: -0.1700

Data Index: 7854690 (Open Web Text)

Max Activating Token Index: 246

Text #7

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.9095. Min Act: -0.1700

Data Index: 5306384 (Open Web Text)

Max Activating Token Index: 463

Text #8

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.9149. Min Act: -0.1700

Data Index: 3849878 (Open Web Text)

Max Activating Token Index: 439

Text #9

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.9144. Min Act: -0.1700

Data Index: 2671312 (Open Web Text)

Max Activating Token Index: 34

Text #10

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.9006. Min Act: -0.1700

Data Index: 2365755 (Open Web Text)

Max Activating Token Index: 947

Text #11

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.9028. Min Act: -0.1700

Data Index: 8258753 (Open Web Text)

Max Activating Token Index: 146

Text #12

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.9125. Min Act: -0.1700

Data Index: 5086586 (Open Web Text)

Max Activating Token Index: 113

Text #13

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.8992. Min Act: -0.1700

Data Index: 2122840 (Open Web Text)

Max Activating Token Index: 416

Text #14

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.9012. Min Act: -0.1700

Data Index: 8818839 (Open Web Text)

Max Activating Token Index: 365

Text #15

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.8945. Min Act: -0.1700

Data Index: 7466317 (Open Web Text)

Max Activating Token Index: 349

Text #16

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.8844. Min Act: -0.1700

Data Index: 7359098 (Open Web Text)

Max Activating Token Index: 124

Text #17

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.8968. Min Act: -0.1700

Data Index: 443623 (Open Web Text)

Max Activating Token Index: 792

Text #18

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.8743. Min Act: -0.1700

Data Index: 4041371 (Open Web Text)

Max Activating Token Index: 28

Text #19

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.8825. Min Act: -0.1700

Data Index: 1628496 (Open Web Text)

Max Activating Token Index: 51